Resource directory
Find what you need for your workflow.
Guides: techniques, setup, and troubleshootingSearch Sweet Tea Pipes, external workflows, models, node packs, and guides in one evidence-linked catalog.
Start with a workflow instead ↗Search results
All resources
20 shown of 41,764
Bredrawz Style (Anima & Illustrious)
Works best at 0.95 weight, 0.5-0.7 weight for Anima.
Aloe v2 Dinov3 Base
ALOEv2 is a B-cos-interpretable DINOv3 model obtained by fine-tuning the original ALOE backbones for a further 30k steps. It keeps the original three-layer distillation scheme but adds per-step multi-resolution...
PupMask
Generating character close-ups is better!
AuraSR
GAN-based Super-Resolution for upscaling generated images, a variation of the GigaGAN paper for image-conditioned upscaling. Torch implementation is based on the unofficial lucidrains/gigagan-pytorch repository.
五線譜&音符🎵 / Five-line Staff & Musical Note ♪
五線譜&音符 / Five-line Staff & Musical Note ♪
ComfyUI_RS_NAI_API_Request
ComfyUI nodes for NovelAI Diffusion V5 and earlier: txt2img, img2img, inpainting, multi-character prompts, sequential YOLO/SAM detailing across multiple regions, automatic character matching with a PyTorch WD tagger,...
Dynamic Portrait Style Enhancer Embedding Pony XL - GlamorShots_PDXL
Use these to ENCHANT, ENHANCE and improve your portraits - it can be used on Realism, Semi Realism and Anime as well - just note that it will create a SEMI REALISTIC anime portrait if you use this. (As in it's styled...
Shirono (oekaki) | Artist Style | GLoRA | ponyXL
Lora trained on oekaki art by shirono ( しろの).
comfyui-image-crop-by-mask-multiple
A ComfyUI custom node based on KJNodes' Image Crop By Mask And Resize, with one added feature: a multiple input that forces the output image, mask, and bbox dimensions to be an exact multiple of a value you choose...
Merger_robyn_carlisle
another merger. really pleased with the outcome on this one
CCAiM
CCAiM aims to develop an AI-powered model for classifying clouds based on ground-level photographs. The project uses image recognition techniques to identify cloud types according to the WMO International Cloud Atlas...
ComfyUI-ListUnwrap
Tiny ComfyUI helper nodes: ListToAudio + ConcatImageBatches for multi-segment MiniMax H3 video stitching
Style - Nep [Anima]
This is an experimental LoRA version trained on Anima Preview .
Dreamshaper XL Lightning Dpmsde
lykon/dreamshaper-xl-lightning is a Stable Diffusion model that has been fine-tuned on stabilityai/stable-diffusion-xl-base-1.0.
Mukuro Ikusaba - Danganronpa
LyCORIS for Mukuro Ikusaba, from Danganronpa Made for this bounty
Suenari Anime Style
The best model in the world: Probably not.
黑塔_herta_(honkai:_star_rail)
kohakudelta使用 Kohaku-XL Delta - rev1 |稳定扩散检查点 |奇维泰
Qwen25 Vl 3b Floorplan Grpo
Improved using Qwen — LoRA adapter continuing from mudasir13cs/qwen25-vl-3b-floorplan-sft; trained with GRPO and geometric rewards. Base checkpoint: Qwen2.5-VL-3B-Instruct (LICENSE).
Hellscape TI Set - HellGirl
Created when I was prompt surfing, saw some really cool basic prompts and wanted to turn them into fun nightmare TIs.
Ahegao v3 (Tongue Out, Cross-eyed) SDXL/Pony 1k
Woah. Flux rips hard when training.
